Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F21%3AA22025BJ" target="_blank" >RIV/61988987:17610/21:A22025BJ - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/article/10.1007/s00521-021-05978-9" target="_blank" >https://link.springer.com/article/10.1007/s00521-021-05978-9</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s00521-021-05978-9" target="_blank" >10.1007/s00521-021-05978-9</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3

Popis výsledku v původním jazyce

We present a new version of YOLO with better performance and extended with instance segmentation called Poly-YOLO. Poly-YOLO builds on the original ideas of YOLOv3 and removes two of its weaknesses: a large amount of rewritten labels and an inefficient distribution of anchors. Poly-YOLO reduces the issues by aggregating features from a light SE-Dark-net-53 backbone with a hypercolumn technique, using stairstep upsampling, and produces a single scale output with high resolution. In comparison with YOLOv3, Poly-YOLO has only 60% of its trainable parameters but improves the mean average precision by a relative 40%. We also present Poly-YOLO lite with fewer parameters and a lower output resolution. It has the same precision as YOLOv3, but it is three times smaller and twice as fast, thus suitable for embedded devices. Finally, Poly-YOLO performs instance segmentation by bounding polygons. The network is trained to detect size-independent polygons defined on a polar grid. Vertices of each polygon are being predicted with their confidence, and therefore Poly-YOLO produces polygons with a varying number of vertices. Source code is available at https://gitlab.com/irafm-ai/poly-yolo.

Název v anglickém jazyce

Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3

Popis výsledku anglicky

We present a new version of YOLO with better performance and extended with instance segmentation called Poly-YOLO. Poly-YOLO builds on the original ideas of YOLOv3 and removes two of its weaknesses: a large amount of rewritten labels and an inefficient distribution of anchors. Poly-YOLO reduces the issues by aggregating features from a light SE-Dark-net-53 backbone with a hypercolumn technique, using stairstep upsampling, and produces a single scale output with high resolution. In comparison with YOLOv3, Poly-YOLO has only 60% of its trainable parameters but improves the mean average precision by a relative 40%. We also present Poly-YOLO lite with fewer parameters and a lower output resolution. It has the same precision as YOLOv3, but it is three times smaller and twice as fast, thus suitable for embedded devices. Finally, Poly-YOLO performs instance segmentation by bounding polygons. The network is trained to detect size-independent polygons defined on a polar grid. Vertices of each polygon are being predicted with their confidence, and therefore Poly-YOLO produces polygons with a varying number of vertices. Source code is available at https://gitlab.com/irafm-ai/poly-yolo.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10102 - Applied mathematics

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

NEURAL COMPUT APPL

ISSN

0941-0643

e-ISSN

1433-3058

Svazek periodika

—

Číslo periodika v rámci svazku

February

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

16

Strana od-do

—

Kód UT WoS článku

000758302200004

EID výsledku v databázi Scopus

2-s2.0-85124764403